desktop-computer SKILL.md skillA

desktop-computer from parcha-ai/agentrun is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add parcha-ai/agentrun/desktop-computer@git:20261115.25c2fb6

Pins git:20261115.25c2fb6 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
parcha-ai/agentrun
Path
packages/serve/src/workspace/kind-skills/desktop/SKILL.md
Versions recorded
6
Latest version
git:20261115.25c2fb6, committed Nov 15, 2026
First version recorded
Nov 10, 2026
Size
11,184 bytes
Repository stars
1,181
License
Apache-2.0

Use a desktop computer (a Mac, or a Linux desktop) through computer_observe, computer_act, computer_screenshot and a codemode script's `computer`. It covers reading an app's elements, acting on them by ref, running known steps as one script, checking what happened, recovering, and reading the computer's refusals. Use when a run has a desktop and the task needs its apps or its windows.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Using a desktop

The run has a desktop, rented while the run lives. You read an app's window as a list of its elements and act on
them by their refs, the way an accessibility tool does. Where the desktop can't list elements (no `ui` group), you see
it through screenshots and act at their pixels. The tools say which one you have.

## The tools

**`computer_observe` `{app?, image?, full?}`** shows an app's window (the one in front when you name none) as compact
lines, one per element:

```
state s3 · com.apple.Notes "Notes" · window "Groceries" 900×700 pt
@e1 window "Groceries"
  @e4 textbox "Title" = "Groceries" [focused]
  @e7 button "Save"
```

Each line is a ref (`@e7`), a role, a name, a value after `=`, what else the element says in parentheses (a help tag)
and flags in brackets. A child is indented under its parent. When an app draws its own window, the computer can't
list its elements: the outline says so, the window's picture comes with it, and you act at points in that picture. The head line names the **state** (`s3`). `image: true` adds the window's picture, which you need only for
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_k3y5my7fnxrnggdb/1ca6bbc55d5cd88b1f838ce4469ec6b2a21c56f43adce240e26e0b1952dbc794.json

Then /plugin install desktop-computer@markdownregistry-k3y5my7fnxrnggdb in Claude Code. It installs git:20261115.25c2fb6, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add parcha-ai/agentrun/desktop-computer@sha256:1ca6bbc55d5cd88b

The line at the top of this page pins the label git:20261115.25c2fb6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_k3y5my7fnxrnggdb.svg)](https://markdownregistry.com/a/art_k3y5my7fnxrnggdb)

5 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in parcha-ai/agentrun/desktop-computer since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of desktop-computer from somewhere else? Ask it: where did my desktop-computer come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 6 versions of this file, between Nov 10, 2026 and Nov 15, 2026, about one every day.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261115.25c2fb6 latest2026-11-15 25c2fb6 11,184 BA view · diff
git:20261115.a8d70fa2026-11-15 a8d70fa 11,054 BA view · diff
git:20261115.2ea8b652026-11-15 2ea8b65 10,654 BA view · diff
git:20261115.6bded562026-11-15 6bded56 10,595 BA view · diff
git:20261115.26d86692026-11-15 26d8669 10,293 BA view · diff
git:20261110.fe825862026-11-10 fe82586 6,512 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11184 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

parcha-ai/agentrun · 1,181 stars · license Apache-2.0 · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_k3y5my7fnxrnggdb
GET https://markdownregistry.com/api/v1/resolve?ref=parcha-ai/agentrun/desktop-computer
GET https://markdownregistry.com/api/v1/blob/1ca6bbc55d5cd88b1f838ce4469ec6b2a21c56f43adce240e26e0b1952dbc794

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from parcha-ai/agentrun

code-review-knowledge SKILL.md skill
parcha-ai/agentrun · .agents/skills/code-review-knowledge/SKILL.md · Invariants and past defect patterns of Parcha-ai/agentrun, keyed by path glob. The code reviewer reads it from the base…
git:20261112.d69251a · audit A · 1,181 stars
gh-stack SKILL.md skill
parcha-ai/agentrun · .agents/skills/gh-stack/SKILL.md · Manage AgentRun's native GitHub PR stacks with gh-stack: inspect, restack, publish and coordinate gated queue…
git:20261114.994ab02 · audit A · 1,181 stars
ship-pr SKILL.md skill
parcha-ai/agentrun · .agents/skills/ship-pr/SKILL.md · The one gate every pull request to Parcha-ai/agentrun passes before it goes to the maintainer: fresh base, local…
git:20261114.994ab02 · audit A · 1,181 stars
ship SKILL.md skill
parcha-ai/agentrun · .agents/skills/ship/SKILL.md · Ship AgentRun work through implementation, proof, review and its merge queue. Use for a named PR, an existing branch or…
git:20261114.994ab02 · audit A · 1,181 stars
AGENTS.md AGENTS.md file
parcha-ai/agentrun · AGENTS.md
git:20261114.994ab02 · audit B · 1,181 stars
CLAUDE.md CLAUDE.md file
parcha-ai/agentrun · CLAUDE.md
git:20261004.5bdb930 · audit B · 1,181 stars
agentrun-setup SKILL.md skill
parcha-ai/agentrun · docs/SKILL.md · Onboard to AgentRun Cloud, local setup or self-hosting by creating a new agent or connecting an existing Claude Code or…
git:20261117.15f5a02 · audit A · 1,181 stars
agentrun-cli SKILL.md skill
parcha-ai/agentrun · packages/agentrun/skills/agentrun-cli/SKILL.md · Onboard and manage AgentRun agents from a shell. Connect existing Claude Code or Codex setups locally or remotely…
git:20261115.039beb7 · audit B · 1,181 stars
agentrun-author SKILL.md skill
parcha-ai/agentrun · packages/dsl/skills/author/SKILL.md · Build, inspect, and run a small AgentRun workflow when the user says /agentrun <task>, asks to use AgentRun, or asks to…
v1.3.0 · audit A · 1,181 stars
agentrun-serve SKILL.md skill
parcha-ai/agentrun · packages/serve/skills/agentrun-serve/SKILL.md · Onboard to AgentRun by starting a new agent, observing agents already running in a backend or terminal, or connecting…
git:20261116.7011bb4 · audit B · 1,181 stars
llms.txt@packages/serve/src llms.txt file
parcha-ai/agentrun · packages/serve/src/llms.txt
git:20261106.9961274 · audit A · 1,181 stars
phone-computer SKILL.md skill
parcha-ai/agentrun · packages/serve/src/workspace/kind-skills/phone/SKILL.md · Use a phone (a cloud Android or an iPhone) through computer_observe, computer_act, computer_screenshot and a codemode…
git:20261115.25c2fb6 · audit A · 1,181 stars

Every file in parcha-ai/agentrun

Browse by kind, by grade A, or by owner.